Today ainotis Join

My notis

ResearchPublished All news from that day

Microsoft Research reports its TokenEconomizer plugin cut coding-agent cost per task by 18.4% to 30.9% on SWE-Bench

The figures are the researchers' own, from a 16 November Microsoft Research post on a paper from UC Berkeley, Microsoft Research and Microsoft Security.

Share

Check our sources · 7 facts from 1 source

Microsoft Research reports that TokenEconomizer, an open-source plugin that learns from a coding agent's past sessions in a repository, cut mean cost per task by 18.4% to 30.9% on SWE-Bench. The result covers 277 tasks in six repositories and five agent-model combinations, and pass@1 rose in four of the five, the researchers say.

The post names Claude Code as the only agent; it does not identify the other four combinations. Profiling Claude Code on 60 SWE-Bench tasks, the researchers found that 30 percent of tool calls repeated an earlier action in the same repository, and that 16 of 23 tool descriptions sent per turn were never called.

On Web-Bench they report costs 16.0% to 21.2% lower, and on security auditing 6.4% to 19.6% lower. They say lowering reasoning effort saved similar or larger amounts but substantially degraded performance. The code is on GitHub at microsoft/TokenEconomizer, and the post says the plugin keeps what it learns on the developer's machine.

Share this story

Your reaction

We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.

Check our sources

Every sentence above is checked against this source.

1 TokenEconomizer: Learning from Experience to Make AI Coding Agents More EfficientMicrosoft Research · 16 Nov 2026 · 7 facts Open the source archived copy
  1. A Microsoft Research blog post of 16 November 2026 describes TokenEconomizer, an open-source plugin from UC Berkeley, Microsoft Research and Microsoft Security that learns from a coding agent's past sessions in a repository to reduce costs in future sessions without modifying the agent or its model.

    TokenEconomizer, an open-source plugin from UC Berkeley, Microsoft Research, and Microsoft Security
    cite
  2. On SWE-Bench (277 tasks, six repositories, five agent-model combinations) the researchers report mean cost per task fell 18.4% to 30.9%, and pass@1 rose in four of the five combinations.

    TokenEconomizer lowered the average cost by 18.4–30.9%.
    cite
  3. The post names Claude Code as the only agent; it does not identify the other four agent-model combinations.

    We first profiled Claude Code on 60 tasks from SWE-Bench.
    cite
  4. The researchers report that in profiling of Claude Code on 60 SWE-Bench tasks, 30% of tool calls repeated an earlier action in the same repository and 16 of 23 tool descriptions sent per turn were never called.

    The agent received 23 tool descriptions on every turn, but 16 were never called.
    cite
  5. The researchers report costs 16.0% to 21.2% lower on Web-Bench and 6.4% to 19.6% lower on security auditing.

    with costs 16.0–21.2% lower on Web-Bench
    cite
  6. The researchers say lowering the model's reasoning effort saved similar or larger amounts but substantially degraded performance.

    lowering the model’s reasoning effort saved similar or larger amounts but led to substantial performance degradation
    cite
  7. The code is at github.com/microsoft/TokenEconomizer, and the post says the plugin keeps what it learns on the developer's machine.

    keeps what it learns on the developer’s machine
    cite

Topics

The morning email

On the mornings we publish: the three top stories and up to four short ones. Free.

We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep